© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 13990
    Prev
    Next
    INDEX
    Explanations

    references to civil rights and health-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    189
    +0.14
    0.8%
    411
    +0.12
    0.7%
    34
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.14
    0.09
    189
    +0.12
    0.06
    411
    +0.12
    0.05
    Negative Logits
    Īĺ
    -2.78
    ±
    -2.78
    ¯
    -2.73
    ¿
    -2.49
    Ŀ
    -2.44
    ı
    -2.42
    ·
    -2.39
    °
    -2.38
    ´
    -2.36
    ³
    -2.29
    POSITIVE LOGITS
     2020
    1.76
     causes
    1.54
     reforms
    1.49
     suffers
    1.46
     coronavirus
    1.44
    Åij
    1.44
     strike
    1.42
     disappears
    1.41
    resis
    1.41
     strikes
    1.39
    Activations Density 0.786%

    No Known Activations